AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Recent Advances in Open Set Recognition: A Survey

Chuanxing Geng, Sheng-Jun Huang, Songcan Chen

TPAMI 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 1,123 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use CD-OSR (HDP-based modeling of unknowns) instead of threshold-based W-SVM at highest opennessnon-depth OSR methods · PENDIGITS (O*=18.35%)micro-F-measure (%): 88.39 -> 98.43Improved
Threshold-based methods as openness increases (W-SVM on LETTER vs PENDIGITS)W-SVM · LETTER and PENDIGITSmicro-F-measure (%)Mixed
Increase openness from O*=0% to 25.46% for 1-vs-Set1-vs-Set · LETTERmicro-F-measure (%): 81.51 -> 42.08Hurt
Use C2AE (split closed-set classification and open-set identification) instead of SoftMaxdeep OSR · CIFAR10 (O*=13.40%)AUROC (%): 67.7 -> 89.5Improved
Joint classification and reconstruction (CROSR) instead of SoftMaxdeep OSR · MNISTAUROC (%): 97.8 -> 99.8Improved
Add instance generation of unknowns (OSRCI) vs C2AEOSRCI · CIFAR+50 (O*=61.51%)AUROC (%): 93.7 -> 82.7Hurt
OpenMax instead of SoftMaxSoftMax · CIFAR+50 (O*=61.51%)AUROC (%): 80.5 -> 79.6No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy